Model comparison
Llama 3-70B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 28.8 | 37.1 |
| Released | 2024-04-18 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.8 (#218), Yi-Lightning: 27.4 (#320)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1206 | 1312 |
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Yi-Lightning: —
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| Cybench | 5% | — |
Reasoning Yi-Lightning leads
Llama 3-70B: 18.0 (#288), Yi-Lightning: 25.9 (#139)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1302 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Yi-Lightning leads
Llama 3-70B: 12.8 (#305), Yi-Lightning: 36.2 (#172)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1218 | 1300 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Yi-Lightning leads
Llama 3-70B: 20.8 (#277), Yi-Lightning: 35.4 (#185)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1149 | 1286 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual Yi-Lightning leads
Llama 3-70B: 33.6 (#251), Yi-Lightning: 42.2 (#196)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1142 | 1269 |
| LMArena Chinese | 1114 | 1320 |
| LMArena French | 1232 | 1305 |
| LMArena German | 1169 | 1267 |
| LMArena Japanese | 1017 | 1228 |
| LMArena Korean | 1017 | 1192 |
| LMArena Russian | 1159 | 1255 |
| LMArena Spanish | 1241 | 1315 |
Instruction Following Yi-Lightning leads
Llama 3-70B: 62.5 (#238), Yi-Lightning: 67.4 (#196)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1194 | 1278 |
Long Context Yi-Lightning leads
Llama 3-70B: 35.6 (#240), Yi-Lightning: 39.4 (#181)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1174 | 1297 |
Writing & Preference Yi-Lightning leads
Llama 3-70B: 42.8 (#231), Yi-Lightning: 50.2 (#184)
| Benchmark | Llama 3-70B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1221 | 1302 |
| LMArena Creative Writing | 1210 | 1280 |
| LMArena Multi-Turn | 1223 | 1311 |
Frequently asked questions
Is Llama 3-70B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.8 on the Noometry Index.
Is Llama 3-70B or Yi-Lightning better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 27.4 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Yi-Lightning share?
17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Yi-Lightning has 18.